Bolt Loosening Detection Using Key-Point Detection Enhanced by Synthetic Datasets
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
Machine vision based on deep learning is gaining more and more applications in structural health monitoring (SHM) due to the rich information that can be achieved in the images. Bolts are widely used in the connection of steel structures, and their loosening can compromise the safety of steel structures and lead to serious accidents. Therefore, this paper proposes a method for the automatic detection of the bolt loosening angle based on the latest key point detection technology using machine vision and deep learning. First, we built a virtual laboratory in Unreal Engine5 that could automatically label and generate synthetic datasets, and the datasets with bolts were collected. Second, the datasets were trained using the YOLOv7-pose framework, and the resulting model was able to accurately detect key points of bolts in images obtained under different angles and lighting conditions. Third, a bolt loosening angle calculation method was proposed according to the detected key points and the position relationship between neighboring bolts. Our results demonstrate that the proposed method is effective at detecting the bolt loosening angle and that the use of synthetic datasets significantly improves the efficiency of datasets establishment while also improving the performance of model training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“DL-based SHM mainly uses structural damage images to classify or segment surface defects to achieve crack detection [130,131,132], bolt loosening detection [47], steel bar exposure detection [49,133], or vehicle recognition through vehicle images captured by road cameras [134,135].”
From Deep Learning for Structural Health Monitoring: Data, Algorithms, Applications, Challenges, and Trends (2023) · cites this paper as [47]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.143 · Cited by 7,539
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2844175 · Cited by 3,457
Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., & Murphy, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_17 · Cited by 621
PifPaf: Composite Fields for Human Pose Estimation
Kreiss, S., Bertoni, L., & Alahi, A. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01225 · Cited by 538
YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss
Maji, D., Nagori, S., Mathew, M., & Poddar, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00297 · Cited by 533
Research works printed but not linked: 2
- Li, 2019, Cascade convolutional neural network based abnormal detection of fasteners, J. Electron. Meas. Instrum., 33, 171
- Wang, C., Alexey, B., and Liao, M.H. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.
Cited by
Jia, J., & Li, Y. (2023) · Sensors · doi:10.3390/s23218824 · Cited by 182
“…defect images of bridges, frame structures, dams, tunnels, and other infrastructures for crack detection [40–44], bolt loosening detection [45–47], rebar surface defect detection [48], delamination and reinforcement exposure detection [49], displacement detection [50–53], voids detection…”
BackgroundMethodQiu, S., Cai, B., Wang, W., Wang, J., Zaheer, Q., Liu, X., Hu, W., & Peng, J. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105363 · Cited by 94
Lin, T.-H., Chang, C.-T., & Putranto, A. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108618 · Cited by 29
Zhang, W., Wan, H., & Todd, M. D. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103373 · Cited by 26
Nieminen, W., Gebreweld, H. B., Liuha, A., Nissinen, M., Verdugo, M., Mikkola, A., & Kutvonen, A. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02795-6 · Cited by 21
A Reliable Bolt Key-Points Detection Method in Industrial Magnetic Separator Systems
Zuo, F., Liu, J., Ren, Y., Wang, L., & Wen, Z. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3547466 · Cited by 16
“In [20], a key-points’ prediction method based on full convolutional architecture was proposed to achieve fast detection.”
A review on vision-based deep learning techniques for damage detection in bolted joints
Malik, Z., Mirani, A., Gopi, T., & Alapati, M. (2024) · Asian Journal of Civil Engineering · doi:10.1007/s42107-024-01139-0 · Cited by 13
“Lu et al. (2023) introduced the bolt-loosening degree detection method using key-point detection technology, which was made possible using computer vision as well as deep learning.”
Golpour, A., Khanzadi, M., & Rahbar, M. (2024) · Journal of Civil Structural Health Monitoring · doi:10.1007/s13349-024-00902-w · Cited by 8
“Lu et al. [20] first built a virtual laboratory in Unreal Engine 5, which helps generate and label a synthetic dataset automatically.”
Training marine species object detectors with synthetic images and unsupervised domain adaptation
Doig, H., Pizarro, O. R., & Williams, S. B. (2025) · Frontiers in Marine Science · doi:10.3389/fmars.2025.1581778 · Cited by 9
A review of AI and machine learning applications in manufacturing processes
Gorine, M. E. A., Nechak, L., Ichchou, M. N., & Pichenot, Y. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02826-2 · Cited by 6
Machine Learning Enabled FBG Optical Sensor Applications
Gupta, S., Kumar, B., & Mishra, S. (2024) · International Conference on Advancements and Key Challenges in Green Energy and Computing (AKGEC) · doi:10.1109/akgec62572.2024.10868970 · Cited by 4
Shan, Z., Dou, H., Wu, F., & Yu, Z. (2025) · Smart Materials and Structures · doi:10.1088/1361-665x/ade6b5 · Cited by 4
“In summary, while Huynh [36] and Lu et al [51] exhibit certain precision advantages under low perspective angles, their robustness to perspective variations remains inferior to our method.”
InfluentialResearch on bolt loosening detection method based on PointNet
Fang, S., Zhao, Q., Zhao, K., & Yang, L. (2025) · IEEE Information Technology and Mechatronics Engineering Conference (ITOEC) · doi:10.1109/itoec63606.2025.10967991 · Cited by 3
“The dataset was trained using the YOLOv7-pose framework, and the resulting model was able to accurately detect bolt key points in images obtained under different angles and lighting conditions [7].”
Efficacy of image based deep learning CNN models for bolt loosening detection in steel structures
Alapati, M., Chandra, G. R., & Abboju, S. (2025) · Asian Journal of Civil Engineering · doi:10.1007/s42107-025-01316-9 · Cited by 2
“(Huynh, 2021; Lu et al., 2023).”
Automated Detection Method for Bolt Detachment of Wind Turbines in Low-Light Scenarios
Deng, J., Yao, Y., Rao, M., Yang, Y., Luo, C., Li, Z., Hua, X., & Chen, B. (2025) · Energies · doi:10.3390/en18092197 · Cited by 2
“To explore the feasibility of the online monitoring of structural bolt defect, many scholars have utilized single-stage algorithms such as you only look once (YOLO) [19–22], Retina-Net [23], and single-shot multibox detector (SSD) [24] to perform regression classi fi cation on structural bolt defect.”
Research on defect detection method of automotive running lights based on keypoint identification
Chen, J., Bai, S., Wan, G., Li, Y., Li, J., & Cheng, Z. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10588328 · Cited by 1
“Lu et al. utilized YOLOv7 to detect six keypoints of bolts to assess for looseness [7].”
MethodYang, J., Ren, G., Huan, Y., Du, W., Xue, S., Wang, B., Cao, S., & Ma, Y. (2025) · Measurement · doi:10.1016/j.measurement.2025.118692 · Cited by 1
Lin, Y., Gao, Y., Fang, C., Lyu, Z., & Cheng, X. (2026) · Structural Health Monitoring · doi:10.1177/14759217251403370 · Cited by 1
Liu, J., Wang, Y., Lang, M., & Zuo, F. (2025) · IEEE Access · doi:10.1109/access.2025.3547332 · Cited by 1
“In [14], a novel structural health monitoring method based on multi-scale YOLO-pose was proposed to detect key points of bolts, effectively improving the feature expression ability of key points.”
InfluentialFish-Tail Bolt Loosening Detection Under Tilted Perspectives
Yu, J., Wu, Q., Xie, K., Cao, Y., Wang, X., Wen, C. B., & Zhang, W. (2025) · Electronics · doi:10.3390/electronics14071281
Spatial Front-Back Relationship Recognition Based on Partition Sorting Network
Gong, P., Zheng, K., Liu, T., Jiang, Y., & Zhao, H. (2025) · Applied Sciences · doi:10.3390/app152111763 · Cited by 1
Luxin, 梁. L., & Yong, 金. J. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop251070
Monocular depth estimation for screw tightness state detection
Wang, J., Shen, N., Gu, M., Shi, J., Li, X., & Chen, K. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae4cae
A Batch Detection Method for Bolt Loosening Angles Based on Machine Vision
Yu, Y., Zhao, Z., Liu, Y., Zhang, C., & Zou, Y. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-981-95-4629-9_31
Kong, X., Liu, J., Liu, Z., He, W., Liu, G., Li, S., Zhao, D., & Zhang, J. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105000
Lin, T.-H., Chen, L., & Putranto, A. (2026) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-18147
Zhang, T., Ran, Y., Gong, H., Wu, T., Ma, T., Guo, J., & Yuan, F. (2026) · Sensors · doi:10.3390/s26175411
“YOLOv5-based marker detection supports angle estimation across changes in distance, viewpoint, and illumination [7], while keypoint methods combined with synthetic data reduce the need for exhaustive physical sampling [8].”
Li, Z., Zhou, D., Liu, Z., & Liu, Q. (2026) · Engineering Research Express · doi:10.1088/2631-8695/aea5e4
Liu, Q., Zhao, C., Xu, K., Wen, Y., & Pei, J. (2026) · Engineering Structures · doi:10.1016/j.engstruct.2026.123750
Metadata
- Authors
- Lu, Q., Jing, Y., & Zhao, X.
- Affiliations
- Dalian University of Technology (CN)
- Corresponding author
- Zhao, Xuefeng
- ORCID
- Zhao, Xuefeng
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2023-02-03
- Volume
- 13
- Issue
- 3
- Pages
- 2020
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4319319095
- Cited by
- 28
- References
- 43
- Citations by year
- 2026: 11 · 2025: 10 · 2024: 6 · 2023: 1
- FWCI
- 3.28
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Mechanical Engineering › Engineering Structural Analysis Methods
- Keywords
- bolt loosening detection, keypoint detection, synthetic data generation, Unreal Engine 5, structural health monitoring, virtual laboratory, machine vision
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.